business-profile-creator
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary function is to conduct a multi-phase interview with the user to define company identity, value propositions, and brand voice. This behavior is transparent and consistent with the described purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface that could potentially be used for indirect prompt injection if the resulting JSON file is processed by other autonomous tools without further sanitization. This is documented as a standard vulnerability surface check.
- Ingestion points: User answers to the interview questions in Phase 1 through Phase 7 (SKILL.md)
- Boundary markers: Not present in the JSON output schema to isolate untrusted user data from structure
- Capability inventory: Ability to write data to the local file system at
/context/business-profile.json - Sanitization: No explicit instructions for input validation, escaping, or filtering of the user-provided responses before they are saved to the configuration file
Audit Metadata